2,560+ academic papers on AI security, attacks, and defenses
Showing 321–340 of 932 papers
Clear filtersSumit Ranjan, Sugandha Sharma, Ubaid Abbas +1 more
Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt...
Chenxi Li, Xianggan Liu, Dake Shen +9 more
Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that...
Yuhang Huang, Boyang Ma, Biwei Yan +5 more
The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external tools and...
Neha Nagaraja, Hayretdin Bahsi
Large Language Models (LLMs) are increasingly integrated into safety-critical workflows, yet existing security analyses remain fragmented and often...
Yige Li, Wei Zhao, Zhe Li +6 more
Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same...
Eduard Hirsch, Kristina Raab, Tobias J. Bauer +1 more
IT systems are facing an increasing number of security threats, including advanced persistent attacks and future quantum-computing vulnerabilities....
Yuxu Ge
Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and...
Punyajoy Saha, Sudipta Halder, Debjyoti Mondal +1 more
Safety alignment is critical for deploying large language models (LLMs) in real-world applications, yet most existing approaches rely on large...
Elzo Brito dos Santos Filho
AI-assisted software generation has increased development speed, but it has also amplified a persistent engineering problem: systems that are...
Donghwa Kang, Hojun Choe, Doohyun Kim +2 more
Deploying deep neural networks (DNNs) on edge devices exposes valuable intellectual property to model-stealing attacks. While TEE-shielded DNN...
Xisen Jin, Michael Duan, Qin Lin +4 more
As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which introduces...
Jinman Wu, Yi Xie, Shen Lin +2 more
Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the...
Ved Sriraman, Adam Block
Best-of-N (BoN) sampling is a widely used inference-time alignment method for language models, whereby N candidate responses are sampled from a...
Xiaoguang Li, Hanyi Wang, Yaowei Huang +6 more
Shuffler-based differential privacy (shuffle-DP) is a privacy paradigm providing high utility by involving a shuffler to permute noisy report from...
Anatoly Belikov, Ilya Fedotov
Large Language Models (LLMs) are increasingly served on shared accelerators where an adversary with read access to device memory can observe KV...
Trapoom Ukarapol, Nut Chukamphaeng, Kunat Pipatanakul +1 more
The safety evaluation of large language models (LLMs) remains largely centered on English, leaving non-English languages and culturally grounded...
Yuchen Shi, Huajie Chen, Heng Xu +6 more
Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources....
G. Madan Mohan, Veena Kiran Nambiar, Kiranmayee Janardhan
We introduce the Dynamic Behavioral Constraint (DBC) benchmark, the first empirical framework for evaluating the efficacy of a structured,...
Geraldin Nanfack, Eugene Belilovsky, Elvis Dohmatob
Safety-aligned language models refuse harmful requests through learned refusal behaviors encoded in their internal representations. Recent...
Kelly L Vomo-Donfack, Adryel Hoszu, Grégory Ginot +1 more
Federated learning (FL) faces two structural tensions: gradient sharing enables data-reconstruction attacks, while non-IID client distributions...
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert